claude

sdlc-agents

10 SDLC workflow agents (BA, SA, architect, designer, coders, testers, reviewer) and 9 reusable skills.

2 on GitHubby Dmitry Volodchenkovv0.6.34MITupdated 4 days ago
/

Plugin sdlc-agents from marketplace sdlc-agents-marketplace in volodchenkov/claude-sdlc-agents. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (12)

  • agent-base

    Use this skill at the start of every Plane Conductor agent run. Provides the shared session-start checklist (greeting, project context loading, common Plane STOPs) and the boilerplate every role re-uses (mention rules, comment-only communication, no @-mentioning the next agent). Read this before doi

  • architecture-review-framework

    Use this skill when working as the architect — reviewing a SPEC produced by the system-analyst, evaluating ADRs, checking cross-trace to REQUIREMENTS, producing ARCH_REVIEW with verdict (APPROVED / CHANGES_REQUIRED) and the SPEC_APPROVED marker. Encodes a 7-area review checklist (Area 0 implementati

  • artifact-templates

    Use this skill when an agent in the Plane Conductor pipeline writes any artifact — REQUIREMENTS, SPEC, ARCH_REVIEW, SPEC_APPROVED marker, Design brief, PLAN, CHANGES, test plan, bug report, REVIEW. Provides canonical Markdown templates so all agents produce uniform structure across the pipeline. Rea

  • babok-elicitation

    Use this skill when working as a Business Analyst (the business-analyst role) — eliciting requirements from stakeholders, structuring requirements per BABOK v3 framework, classifying needs by type (Business / Stakeholder / Solution / Transition), and applying analysis techniques (5 Whys, MoSCoW, INV

  • code-review-discipline

    Use this skill when working as the final Reviewer (the reviewer role) — comprehensive cross-cutting review before closing a Plane issue. Encodes OWASP Top 10 (security), SOLID principles (code quality), Google engineering practices (review checklist), cross-trace validation between REQUIREMENTS, SPE

  • documentation-discipline

    Use this skill when working as a coder (the django-developer / the vue-developer / the react-developer) and your implementation is complete — what documentation to update, where, and how. Covers docstrings, README updates, API endpoint docs, ADR status updates, migration notes, inline comments. The

  • iac-discipline

    Use this skill when working on Yandex Cloud infrastructure — provisioning clusters, databases, buckets, VMs; writing OpenTofu / Argo CD / Crossplane; setting up GitLab CI pipelines for infra; onboarding a new tenant; or reviewing a `tofu plan`. Encodes the modern 2026 default stack (OpenTofu Stacks

  • istqb-test-design

    Use this skill when working as a tester (the api-tester for API testing, the ui-tester for UX/E2E testing) — designing test cases per ISTQB Foundation framework, choosing the right test design technique (Equivalence Partitioning, Boundary Value Analysis, Decision Table, State Transition, Use Case Te

  • plane-operations

    Use this skill whenever an agent interacts with Plane (https://plane.so) — picking up issues, creating sub-issues for artifacts, posting comments, finding artifacts by label, mentioning users, handling re-entry (continuation vs rework), or completing work. Triggers on any usage of mcp__plane__* tool

  • step-execution-discipline

    Use this skill when a coder (django-developer / vue-developer / react-developer) or a tester (api-tester / ui-tester) executes a multi-step PLAN. Encodes (a) how to size steps with the 5-budget AND-filter and vertical-slice rule, (b) the one-step-per-invocation loop with checkbox state in PLAN sub-i

  • system-design-techniques

    Use this skill when working as the system-analyst — translating REQUIREMENTS into a technical SPEC. Encodes C4 Model for architecture views, DDD bounded contexts for service mapping, REST API design conventions, IEEE 29148 terminology, and ADR (Architecture Decision Records) pattern. Read before com

  • ux-design-discipline

    Use this skill when working as the designer — producing UX flow + Figma frame inventory for SPEC implementation, evaluating accessibility (WCAG 2.1 AA), applying Nielsen usability heuristics, choosing platform conventions (Material 3 web / iOS HIG / desktop). Also covers UX-Review mode — verifying f

Subagents (13)

  • api-tester

    API Tester agent. Use when backend code (CHANGES from a backend developer) is ready and the REST API needs system-level testing — endpoint behaviour, status codes, idempotency, multitenancy, performance smoke. Designs test cases per ISTQB Foundation framework.

  • architect

    Architect agent. Use when SPEC is ready by the system-analyst and needs an ARCH_REVIEW — service boundaries, multitenancy, performance, transactions, integration security, migrations, ADR governance, traceability validation. Produces verdict APPROVED / CHANGES_REQUIRED.

  • business-analyst

    Business Analyst agent. Use when a new product task arrives in Plane and requirements need to be elicited from the initiator and structured into the root issue description per BABOK v3 framework.

  • designer

    UX/UI Designer agent. Two modes — Mode A (Design brief): produce UX flow + Figma frame inventory before frontend coding. Mode B (UX review): verify frontend implementation matches design intent. Follows Nielsen heuristics + WCAG 2.1 + platform conventions.

  • devops-engineer

    DevOps / Cloud Infrastructure engineer. Use when SPEC is approved by the architect and infrastructure code needs to be written — OpenTofu modules, Argo CD apps, Crossplane compositions, GitLab CI pipelines for infra, YC resource provisioning, k8s cluster bootstrap, tenant onboarding. Never applies c

  • django-developer

    Django/DRF backend developer. Use when SPEC is approved by the architect and Django code needs to be written — models, views, serializers, Celery tasks, migrations.

  • project-manager

    Tron — personal tech lead. Takes the user's request, files it in Plane and starts the SDLC pipeline (business-analyst → system-analyst → architect → coders → testers → reviewer), relays the three human gates (requirements, SPEC, implementation) and the answers to them, fixes small things directly in

  • zuse

    Prompt Architect. Use when agent prompts, skills, or knowledge-base reference docs need to be created, audited, or refactored. Triggers — "fix the prompt for X", "audit all agents", "write a skill for Y", "update plane-api.md".

  • react-developer

    React Developer agent. Use when SPEC is approved and React / Next.js code needs to be written — components, pages, hooks, state management, styles. Modern React 18+ with hooks; Next.js 14+ App Router by default.

  • reviewer

    Final Reviewer agent. Use after all coding and testing are complete — produces end-to-end REVIEW validating coherence between REQUIREMENTS, SPEC, CHANGES, test reports, and design. Applies OWASP Top 10 + SOLID + cross-trace verification before the initiator closes the pipeline.

  • system-analyst

    System Analyst agent. Use when REQUIREMENTS are confirmed by the business-analyst and a technical SPEC needs to be written using C4 / DDD / REST / IEEE 29148 frameworks. Phase-decomposed into 6 interview/draft passes.

  • ui-tester

    UX / E2E Tester agent. Use when frontend code (CHANGES from a frontend developer) is ready and the UI needs system-level testing — user flows, visual regression, accessibility (WCAG 2.1), browser compatibility. Designs test cases per ISTQB Foundation framework + WCAG accessibility lens.

  • vue-developer

    Vue Developer agent. Use when SPEC is approved and Vue/Nuxt code needs to be written. Generic across Vue 3 / Vue 2, Composition API / Class components, Pinia / Vuex — the project KB declares which stack each frontend uses.

View source on GitHub

Maintain sdlc-agents?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted